Matches in SemOpenAlex for { <https://semopenalex.org/work/W2040649920> ?p ?o ?g. }
- W2040649920 abstract "We consider the problem of learning incoherent sparse and low-rank patterns from multiple tasks. Our approach is based on a linear multi-task learning formulation, in which the sparse and low-rank patterns are induced by a cardinality regularization term and a low-rank constraint, respectively. This formulation is non-convex; we convert it into its convex surrogate, which can be routinely solved via semidefinite programming for small-size problems. We propose to employ the general projected gradient scheme to efficiently solve such a convex surrogate; however, in the optimization formulation, the objective function is non-differentiable and the feasible domain is non-trivial. We present the procedures for computing the projected gradient and ensuring the global convergence of the projected gradient scheme. The computation of projected gradient involves a constrained optimization problem; we show that the optimal solution to such a problem can be obtained via solving an unconstrained optimization subproblem and an Euclidean projection subproblem. In addition, we present two projected gradient algorithms and discuss their rates of convergence. Experimental results on benchmark data sets demonstrate the effectiveness of the proposed multi-task learning formulation and the efficiency of the proposed projected gradient algorithms." @default.
- W2040649920 created "2016-06-24" @default.
- W2040649920 creator A5010419481 @default.
- W2040649920 creator A5049225160 @default.
- W2040649920 creator A5081340408 @default.
- W2040649920 date "2010-07-25" @default.
- W2040649920 modified "2023-09-26" @default.
- W2040649920 title "Learning incoherent sparse and low-rank patterns from multiple tasks" @default.
- W2040649920 cites W1966096622 @default.
- W2040649920 cites W1968398095 @default.
- W2040649920 cites W1986744686 @default.
- W2040649920 cites W1998635907 @default.
- W2040649920 cites W2029970906 @default.
- W2040649920 cites W2030290736 @default.
- W2040649920 cites W2045704273 @default.
- W2040649920 cites W2065180801 @default.
- W2040649920 cites W2100556411 @default.
- W2040649920 cites W2115807064 @default.
- W2040649920 cites W2119187866 @default.
- W2040649920 cites W2130903752 @default.
- W2040649920 cites W2132345820 @default.
- W2040649920 cites W2133491790 @default.
- W2040649920 cites W2144752499 @default.
- W2040649920 cites W2148522164 @default.
- W2040649920 cites W2159514083 @default.
- W2040649920 cites W2162854380 @default.
- W2040649920 cites W2557168633 @default.
- W2040649920 cites W2912522929 @default.
- W2040649920 cites W2913340405 @default.
- W2040649920 cites W3009608574 @default.
- W2040649920 cites W3010453621 @default.
- W2040649920 cites W3011040805 @default.
- W2040649920 doi "https://doi.org/10.1145/1835804.1835952" @default.
- W2040649920 hasPublicationYear "2010" @default.
- W2040649920 type Work @default.
- W2040649920 sameAs 2040649920 @default.
- W2040649920 citedByCount "75" @default.
- W2040649920 countsByYear W20406499202012 @default.
- W2040649920 countsByYear W20406499202013 @default.
- W2040649920 countsByYear W20406499202014 @default.
- W2040649920 countsByYear W20406499202015 @default.
- W2040649920 countsByYear W20406499202016 @default.
- W2040649920 countsByYear W20406499202017 @default.
- W2040649920 countsByYear W20406499202018 @default.
- W2040649920 countsByYear W20406499202020 @default.
- W2040649920 countsByYear W20406499202021 @default.
- W2040649920 countsByYear W20406499202022 @default.
- W2040649920 countsByYear W20406499202023 @default.
- W2040649920 crossrefType "proceedings-article" @default.
- W2040649920 hasAuthorship W2040649920A5010419481 @default.
- W2040649920 hasAuthorship W2040649920A5049225160 @default.
- W2040649920 hasAuthorship W2040649920A5081340408 @default.
- W2040649920 hasBestOaLocation W20406499202 @default.
- W2040649920 hasConcept C10494615 @default.
- W2040649920 hasConcept C112680207 @default.
- W2040649920 hasConcept C11413529 @default.
- W2040649920 hasConcept C115680565 @default.
- W2040649920 hasConcept C126255220 @default.
- W2040649920 hasConcept C137836250 @default.
- W2040649920 hasConcept C145446738 @default.
- W2040649920 hasConcept C153258448 @default.
- W2040649920 hasConcept C154945302 @default.
- W2040649920 hasConcept C157972887 @default.
- W2040649920 hasConcept C2524010 @default.
- W2040649920 hasConcept C2776135515 @default.
- W2040649920 hasConcept C33923547 @default.
- W2040649920 hasConcept C41008148 @default.
- W2040649920 hasConcept C41045048 @default.
- W2040649920 hasConcept C50644808 @default.
- W2040649920 hasConceptScore W2040649920C10494615 @default.
- W2040649920 hasConceptScore W2040649920C112680207 @default.
- W2040649920 hasConceptScore W2040649920C11413529 @default.
- W2040649920 hasConceptScore W2040649920C115680565 @default.
- W2040649920 hasConceptScore W2040649920C126255220 @default.
- W2040649920 hasConceptScore W2040649920C137836250 @default.
- W2040649920 hasConceptScore W2040649920C145446738 @default.
- W2040649920 hasConceptScore W2040649920C153258448 @default.
- W2040649920 hasConceptScore W2040649920C154945302 @default.
- W2040649920 hasConceptScore W2040649920C157972887 @default.
- W2040649920 hasConceptScore W2040649920C2524010 @default.
- W2040649920 hasConceptScore W2040649920C2776135515 @default.
- W2040649920 hasConceptScore W2040649920C33923547 @default.
- W2040649920 hasConceptScore W2040649920C41008148 @default.
- W2040649920 hasConceptScore W2040649920C41045048 @default.
- W2040649920 hasConceptScore W2040649920C50644808 @default.
- W2040649920 hasLocation W20406499201 @default.
- W2040649920 hasLocation W20406499202 @default.
- W2040649920 hasOpenAccess W2040649920 @default.
- W2040649920 hasPrimaryLocation W20406499201 @default.
- W2040649920 hasRelatedWork W2009182781 @default.
- W2040649920 hasRelatedWork W2037966176 @default.
- W2040649920 hasRelatedWork W2170262790 @default.
- W2040649920 hasRelatedWork W25321933 @default.
- W2040649920 hasRelatedWork W2594900731 @default.
- W2040649920 hasRelatedWork W2796161934 @default.
- W2040649920 hasRelatedWork W2980324662 @default.
- W2040649920 hasRelatedWork W4318347891 @default.
- W2040649920 hasRelatedWork W4372267246 @default.
- W2040649920 hasRelatedWork W4385644471 @default.
- W2040649920 isParatext "false" @default.